US Patent 10922734 Automatic identification of issues in text-based transcripts

A computerized method is provided for automatically identifying a set of historical issues derived from historical customer interactions with an enterprise. The method includes collecting text-based data corresponding to the historical customer interactions, extracting customer queries from the text-based data, and normalizing and filtering the customer queries to generate the set of historical issues of the customer queries. The method also includes assigning the historical issues to one or more clusters that capture variances among the historical issues. The method further includes generating a legitimacy score for each historical issue and ranking the set of historical issues in accordance with their corresponding legitimacy scores. The method can further include identifying one or more issues in a transcript of unstructured text using the set of historical issues.